tungsten-logo
Sign In
realvision-xl
realvision-xl

realvision-xl

7 stars
Version: v3.0
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
width
Output image width
height
Output image height
enhance_face_with_adetailer
Enhance face with adetailer
enhance_hands_with_adetailer
Enhance hands with adetailer
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
detail
Enhance/diminish detail while keeping the overall style/character
brightness
Adjust brightness
contrast
Adjust contrast
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
sampler
Sampler type
samping_steps
Number of denoising steps
cfg_scale
Scale for classifier-free guidance
clip_skip
The number of last layers of CLIP network to skip
vae
Select VAE
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
Sign in to run this model for free!
Output
https://files.tungsten.run/uploads/6d861800447d4913a3ab75cfff2a4e26/00000-2649040867.webp
https://files.tungsten.run/uploads/17ca7a071ad9497085e5aeda7e02d6bc/00001-2649040868.webp
https://files.tungsten.run/uploads/d8d4442ee18640298b2b49ac8e4dc8e1/00002-2649040869.webp
This example was created by evevalentine2017
Finished in 393.6 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: Cyberpunk style scenery, neon, dystopian, futuristic, vibrant, detailed, high contrast, reminiscent of cyberpunk genre, dynamic pose, neon green and purple hue, in the style of Nicola Samor Full negative prompt: text, watermark, undersaturated colors, washed out, static, still, instantaneous, unchanging, camera, blurry 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:04<02:39, 4.09s/it] 5%|▌ | 2/40 [00:09<02:58, 4.71s/it] 8%|▊ | 3/40 [00:14<03:08, 5.10s/it] 10%|█ | 4/40 [00:20<03:10, 5.30s/it] 12%|█▎ | 5/40 [00:25<03:08, 5.39s/it] 15%|█▌ | 6/40 [00:31<03:03, 5.39s/it] 18%|█▊ | 7/40 [00:37<03:01, 5.50s/it] 20%|██ | 8/40 [00:42<02:53, 5.43s/it] 22%|██▎ | 9/40 [00:47<02:47, 5.40s/it] 25%|██▌ | 10/40 [00:52<02:40, 5.37s/it] 28%|██▊ | 11/40 [00:58<02:34, 5.33s/it] 30%|███ | 12/40 [01:03<02:30, 5.39s/it] 32%|███▎ | 13/40 [01:09<02:24, 5.37s/it] 35%|███▌ | 14/40 [01:14<02:17, 5.30s/it] 38%|███▊ | 15/40 [01:19<02:13, 5.34s/it] 40%|████ | 16/40 [01:24<02:07, 5.31s/it] 42%|████▎ | 17/40 [01:30<02:02, 5.34s/it] 45%|████▌ | 18/40 [01:35<01:57, 5.32s/it] 48%|████▊ | 19/40 [01:41<01:52, 5.36s/it] 50%|█████ | 20/40 [01:46<01:46, 5.30s/it] 52%|█████▎ | 21/40 [01:50<01:36, 5.10s/it] 55%|█████▌ | 22/40 [01:55<01:26, 4.82s/it] 57%|█████▊ | 23/40 [02:00<01:24, 4.96s/it] 60%|██████ | 24/40 [02:05<01:21, 5.12s/it] 62%|██████▎ | 25/40 [02:10<01:13, 4.89s/it] 65%|██████▌ | 26/40 [02:15<01:08, 4.90s/it] 68%|██████▊ | 27/40 [02:20<01:04, 4.97s/it] 70%|███████ | 28/40 [02:24<00:58, 4.85s/it] 72%|███████▎ | 29/40 [02:29<00:53, 4.89s/it] 75%|███████▌ | 30/40 [02:35<00:51, 5.18s/it] 78%|███████▊ | 31/40 [02:39<00:44, 4.92s/it] 80%|████████ | 32/40 [02:43<00:36, 4.62s/it] 82%|████████▎ | 33/40 [02:48<00:31, 4.57s/it] 85%|████████▌ | 34/40 [02:52<00:26, 4.42s/it] 88%|████████▊ | 35/40 [02:56<00:22, 4.46s/it] 90%|█████████ | 36/40 [03:00<00:17, 4.28s/it] 92%|█████████▎| 37/40 [03:05<00:12, 4.27s/it] 95%|█████████▌| 38/40 [03:09<00:08, 4.22s/it] 98%|█████████▊| 39/40 [03:12<00:04, 4.02s/it] 100%|██████████| 40/40 [03:13<00:00, 3.21s/it] 100%|██████████| 40/40 [03:13<00:00, 4.85s/it] Decoding latents in cuda:0... done in 2.36s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.6ms Speed: 3.7ms preprocess, 7.6ms inference, 25.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:01<00:25, 1.40s/it] 11%|█ | 2/19 [00:02<00:25, 1.51s/it] 16%|█▌ | 3/19 [00:04<00:25, 1.61s/it] 21%|██ | 4/19 [00:06<00:22, 1.49s/it] 26%|██▋ | 5/19 [00:07<00:20, 1.50s/it] 32%|███▏ | 6/19 [00:09<00:19, 1.52s/it] 37%|███▋ | 7/19 [00:10<00:17, 1.49s/it] 42%|████▏ | 8/19 [00:12<00:16, 1.51s/it] 47%|████▋ | 9/19 [00:13<00:15, 1.54s/it] 53%|█████▎ | 10/19 [00:14<00:13, 1.46s/it] 58%|█████▊ | 11/19 [00:16<00:10, 1.37s/it] 63%|██████▎ | 12/19 [00:17<00:09, 1.37s/it] 68%|██████▊ | 13/19 [00:18<00:07, 1.32s/it] 74%|███████▎ | 14/19 [00:20<00:06, 1.32s/it] 79%|███████▉ | 15/19 [00:21<00:05, 1.27s/it] 84%|████████▍ | 16/19 [00:22<00:03, 1.28s/it] 89%|████████▉ | 17/19 [00:23<00:02, 1.27s/it] 95%|█████████▍| 18/19 [00:24<00:01, 1.21s/it] 100%|██████████| 19/19 [00:25<00:00, 1.04it/s] 100%|██████████| 19/19 [00:25<00:00, 1.33s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.3ms Speed: 3.2ms preprocess, 7.3ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:01<00:23, 1.32s/it] 11%|█ | 2/19 [00:02<00:25, 1.49s/it] 16%|█▌ | 3/19 [00:04<00:25, 1.60s/it] 21%|██ | 4/19 [00:06<00:22, 1.51s/it] 26%|██▋ | 5/19 [00:07<00:21, 1.51s/it] 32%|███▏ | 6/19 [00:09<00:19, 1.54s/it] 37%|███▋ | 7/19 [00:10<00:17, 1.50s/it] 42%|████▏ | 8/19 [00:12<00:16, 1.51s/it] 47%|████▋ | 9/19 [00:13<00:15, 1.54s/it] 53%|█████▎ | 10/19 [00:14<00:13, 1.46s/it] 58%|█████▊ | 11/19 [00:16<00:10, 1.37s/it] 63%|██████▎ | 12/19 [00:17<00:09, 1.36s/it] 68%|██████▊ | 13/19 [00:18<00:07, 1.31s/it] 74%|███████▎ | 14/19 [00:20<00:06, 1.31s/it] 79%|███████▉ | 15/19 [00:21<00:05, 1.27s/it] 84%|████████▍ | 16/19 [00:22<00:03, 1.27s/it] 89%|████████▉ | 17/19 [00:23<00:02, 1.27s/it] 95%|█████████▍| 18/19 [00:24<00:01, 1.21s/it] 100%|██████████| 19/19 [00:25<00:00, 1.04it/s] 100%|██████████| 19/19 [00:25<00:00, 1.32s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:01<00:24, 1.35s/it] 11%|█ | 2/19 [00:02<00:25, 1.50s/it] 16%|█▌ | 3/19 [00:04<00:25, 1.59s/it] 21%|██ | 4/19 [00:05<00:22, 1.49s/it] 26%|██▋ | 5/19 [00:07<00:21, 1.50s/it] 32%|███▏ | 6/19 [00:09<00:19, 1.54s/it] 37%|███▋ | 7/19 [00:10<00:17, 1.50s/it] 42%|████▏ | 8/19 [00:12<00:16, 1.52s/it] 47%|████▋ | 9/19 [00:13<00:15, 1.55s/it] 53%|█████▎ | 10/19 [00:15<00:13, 1.47s/it] 58%|█████▊ | 11/19 [00:16<00:11, 1.38s/it] 63%|██████▎ | 12/19 [00:17<00:09, 1.38s/it] 68%|██████▊ | 13/19 [00:18<00:07, 1.32s/it] 74%|███████▎ | 14/19 [00:20<00:06, 1.33s/it] 79%|███████▉ | 15/19 [00:21<00:05, 1.28s/it] 84%|████████▍ | 16/19 [00:22<00:03, 1.29s/it] 89%|████████▉ | 17/19 [00:23<00:02, 1.29s/it] 95%|█████████▍| 18/19 [00:24<00:01, 1.24s/it] 100%|██████████| 19/19 [00:25<00:00, 1.02it/s] 100%|██████████| 19/19 [00:25<00:00, 1.34s/it] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 3.0ms preprocess, 7.4ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:01<00:23, 1.33s/it] 11%|█ | 2/19 [00:02<00:25, 1.48s/it] 16%|█▌ | 3/19 [00:04<00:25, 1.59s/it] 21%|██ | 4/19 [00:05<00:22, 1.49s/it] 26%|██▋ | 5/19 [00:07<00:20, 1.50s/it] 32%|███▏ | 6/19 [00:09<00:19, 1.52s/it] 37%|███▋ | 7/19 [00:10<00:17, 1.48s/it] 42%|████▏ | 8/19 [00:11<00:16, 1.50s/it] 47%|████▋ | 9/19 [00:13<00:15, 1.54s/it] 53%|█████▎ | 10/19 [00:14<00:13, 1.46s/it] 58%|█████▊ | 11/19 [00:16<00:11, 1.38s/it] 63%|██████▎ | 12/19 [00:17<00:09, 1.38s/it] 68%|██████▊ | 13/19 [00:18<00:07, 1.33s/it] 74%|███████▎ | 14/19 [00:20<00:06, 1.33s/it] 79%|███████▉ | 15/19 [00:21<00:05, 1.28s/it] 84%|████████▍ | 16/19 [00:22<00:03, 1.28s/it] 89%|████████▉ | 17/19 [00:23<00:02, 1.28s/it] 95%|█████████▍| 18/19 [00:24<00:01, 1.22s/it] 100%|██████████| 19/19 [00:25<00:00, 1.03it/s] 100%|██████████| 19/19 [00:25<00:00, 1.33s/it] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.1ms Speed: 3.3ms preprocess, 7.1ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:01<00:24, 1.37s/it] 11%|█ | 2/19 [00:03<00:26, 1.54s/it] 16%|█▌ | 3/19 [00:04<00:25, 1.62s/it] 21%|██ | 4/19 [00:06<00:22, 1.51s/it] 26%|██▋ | 5/19 [00:07<00:21, 1.51s/it] 32%|███▏ | 6/19 [00:09<00:19, 1.54s/it] 37%|███▋ | 7/19 [00:10<00:17, 1.50s/it] 42%|████▏ | 8/19 [00:12<00:16, 1.51s/it] 47%|████▋ | 9/19 [00:13<00:15, 1.53s/it] 53%|█████▎ | 10/19 [00:14<00:13, 1.46s/it] 58%|█████▊ | 11/19 [00:16<00:10, 1.37s/it] 63%|██████▎ | 12/19 [00:17<00:09, 1.36s/it] 68%|██████▊ | 13/19 [00:18<00:07, 1.31s/it] 74%|███████▎ | 14/19 [00:20<00:06, 1.31s/it] 79%|███████▉ | 15/19 [00:21<00:05, 1.27s/it] 84%|████████▍ | 16/19 [00:22<00:03, 1.27s/it] 89%|████████▉ | 17/19 [00:23<00:02, 1.27s/it] 95%|█████████▍| 18/19 [00:24<00:01, 1.21s/it] 100%|██████████| 19/19 [00:25<00:00, 1.04it/s] 100%|██████████| 19/19 [00:25<00:00, 1.33s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 2 faces, 7.5ms Speed: 3.0ms preprocess, 7.5ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:01<00:23, 1.32s/it] 11%|█ | 2/19 [00:02<00:25, 1.48s/it] 16%|█▌ | 3/19 [00:04<00:25, 1.58s/it] 21%|██ | 4/19 [00:05<00:22, 1.48s/it] 26%|██▋ | 5/19 [00:07<00:20, 1.49s/it] 32%|███▏ | 6/19 [00:09<00:19, 1.52s/it] 37%|███▋ | 7/19 [00:10<00:17, 1.48s/it] 42%|████▏ | 8/19 [00:11<00:16, 1.50s/it] 47%|████▋ | 9/19 [00:13<00:15, 1.52s/it] 53%|█████▎ | 10/19 [00:14<00:13, 1.45s/it] 58%|█████▊ | 11/19 [00:15<00:10, 1.36s/it] 63%|██████▎ | 12/19 [00:17<00:09, 1.36s/it] 68%|██████▊ | 13/19 [00:18<00:07, 1.31s/it] 74%|███████▎ | 14/19 [00:19<00:06, 1.31s/it] 79%|███████▉ | 15/19 [00:20<00:05, 1.26s/it] 84%|████████▍ | 16/19 [00:22<00:03, 1.28s/it] 89%|████████▉ | 17/19 [00:23<00:02, 1.28s/it] 95%|█████████▍| 18/19 [00:24<00:01, 1.22s/it] 100%|██████████| 19/19 [00:25<00:00, 1.03it/s] 100%|██████████| 19/19 [00:25<00:00, 1.32s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:01<00:24, 1.36s/it] 11%|█ | 2/19 [00:03<00:26, 1.56s/it] 16%|█▌ | 3/19 [00:04<00:26, 1.65s/it] 21%|██ | 4/19 [00:06<00:22, 1.53s/it] 26%|██▋ | 5/19 [00:07<00:21, 1.52s/it] 32%|███▏ | 6/19 [00:09<00:20, 1.57s/it] 37%|███▋ | 7/19 [00:10<00:18, 1.52s/it] 42%|████▏ | 8/19 [00:12<00:16, 1.53s/it] 47%|████▋ | 9/19 [00:13<00:15, 1.56s/it] 53%|█████▎ | 10/19 [00:15<00:13, 1.48s/it] 58%|█████▊ | 11/19 [00:16<00:11, 1.39s/it] 63%|██████▎ | 12/19 [00:17<00:09, 1.38s/it] 68%|██████▊ | 13/19 [00:18<00:07, 1.33s/it] 74%|███████▎ | 14/19 [00:20<00:06, 1.34s/it] 79%|███████▉ | 15/19 [00:21<00:05, 1.29s/it] 84%|████████▍ | 16/19 [00:22<00:03, 1.29s/it] 89%|████████▉ | 17/19 [00:24<00:02, 1.28s/it] 95%|█████████▍| 18/19 [00:25<00:01, 1.22s/it] 100%|██████████| 19/19 [00:25<00:00, 1.03it/s] 100%|██████████| 19/19 [00:25<00:00, 1.34s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.1ms Speed: 3.1ms preprocess, 7.1ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. Uploading outputs... Finished.
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
width
Output image width
height
Output image height
enhance_face_with_adetailer
Enhance face with adetailer
enhance_hands_with_adetailer
Enhance hands with adetailer
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
detail
Enhance/diminish detail while keeping the overall style/character
brightness
Adjust brightness
contrast
Adjust contrast
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
sampler
Sampler type
samping_steps
Number of denoising steps
cfg_scale
Scale for classifier-free guidance
clip_skip
The number of last layers of CLIP network to skip
vae
Select VAE
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
Sign in to run this model for free!
https://files.tungsten.run/uploads/6d861800447d4913a3ab75cfff2a4e26/00000-2649040867.webp
https://files.tungsten.run/uploads/17ca7a071ad9497085e5aeda7e02d6bc/00001-2649040868.webp
https://files.tungsten.run/uploads/d8d4442ee18640298b2b49ac8e4dc8e1/00002-2649040869.webp
This example was created by evevalentine2017
Finished in 393.6 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: Cyberpunk style scenery, neon, dystopian, futuristic, vibrant, detailed, high contrast, reminiscent of cyberpunk genre, dynamic pose, neon green and purple hue, in the style of Nicola Samor Full negative prompt: text, watermark, undersaturated colors, washed out, static, still, instantaneous, unchanging, camera, blurry 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:04<02:39, 4.09s/it] 5%|▌ | 2/40 [00:09<02:58, 4.71s/it] 8%|▊ | 3/40 [00:14<03:08, 5.10s/it] 10%|█ | 4/40 [00:20<03:10, 5.30s/it] 12%|█▎ | 5/40 [00:25<03:08, 5.39s/it] 15%|█▌ | 6/40 [00:31<03:03, 5.39s/it] 18%|█▊ | 7/40 [00:37<03:01, 5.50s/it] 20%|██ | 8/40 [00:42<02:53, 5.43s/it] 22%|██▎ | 9/40 [00:47<02:47, 5.40s/it] 25%|██▌ | 10/40 [00:52<02:40, 5.37s/it] 28%|██▊ | 11/40 [00:58<02:34, 5.33s/it] 30%|███ | 12/40 [01:03<02:30, 5.39s/it] 32%|███▎ | 13/40 [01:09<02:24, 5.37s/it] 35%|███▌ | 14/40 [01:14<02:17, 5.30s/it] 38%|███▊ | 15/40 [01:19<02:13, 5.34s/it] 40%|████ | 16/40 [01:24<02:07, 5.31s/it] 42%|████▎ | 17/40 [01:30<02:02, 5.34s/it] 45%|████▌ | 18/40 [01:35<01:57, 5.32s/it] 48%|████▊ | 19/40 [01:41<01:52, 5.36s/it] 50%|█████ | 20/40 [01:46<01:46, 5.30s/it] 52%|█████▎ | 21/40 [01:50<01:36, 5.10s/it] 55%|█████▌ | 22/40 [01:55<01:26, 4.82s/it] 57%|█████▊ | 23/40 [02:00<01:24, 4.96s/it] 60%|██████ | 24/40 [02:05<01:21, 5.12s/it] 62%|██████▎ | 25/40 [02:10<01:13, 4.89s/it] 65%|██████▌ | 26/40 [02:15<01:08, 4.90s/it] 68%|██████▊ | 27/40 [02:20<01:04, 4.97s/it] 70%|███████ | 28/40 [02:24<00:58, 4.85s/it] 72%|███████▎ | 29/40 [02:29<00:53, 4.89s/it] 75%|███████▌ | 30/40 [02:35<00:51, 5.18s/it] 78%|███████▊ | 31/40 [02:39<00:44, 4.92s/it] 80%|████████ | 32/40 [02:43<00:36, 4.62s/it] 82%|████████▎ | 33/40 [02:48<00:31, 4.57s/it] 85%|████████▌ | 34/40 [02:52<00:26, 4.42s/it] 88%|████████▊ | 35/40 [02:56<00:22, 4.46s/it] 90%|█████████ | 36/40 [03:00<00:17, 4.28s/it] 92%|█████████▎| 37/40 [03:05<00:12, 4.27s/it] 95%|█████████▌| 38/40 [03:09<00:08, 4.22s/it] 98%|█████████▊| 39/40 [03:12<00:04, 4.02s/it] 100%|██████████| 40/40 [03:13<00:00, 3.21s/it] 100%|██████████| 40/40 [03:13<00:00, 4.85s/it] Decoding latents in cuda:0... done in 2.36s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.6ms Speed: 3.7ms preprocess, 7.6ms inference, 25.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:01<00:25, 1.40s/it] 11%|█ | 2/19 [00:02<00:25, 1.51s/it] 16%|█▌ | 3/19 [00:04<00:25, 1.61s/it] 21%|██ | 4/19 [00:06<00:22, 1.49s/it] 26%|██▋ | 5/19 [00:07<00:20, 1.50s/it] 32%|███▏ | 6/19 [00:09<00:19, 1.52s/it] 37%|███▋ | 7/19 [00:10<00:17, 1.49s/it] 42%|████▏ | 8/19 [00:12<00:16, 1.51s/it] 47%|████▋ | 9/19 [00:13<00:15, 1.54s/it] 53%|█████▎ | 10/19 [00:14<00:13, 1.46s/it] 58%|█████▊ | 11/19 [00:16<00:10, 1.37s/it] 63%|██████▎ | 12/19 [00:17<00:09, 1.37s/it] 68%|██████▊ | 13/19 [00:18<00:07, 1.32s/it] 74%|███████▎ | 14/19 [00:20<00:06, 1.32s/it] 79%|███████▉ | 15/19 [00:21<00:05, 1.27s/it] 84%|████████▍ | 16/19 [00:22<00:03, 1.28s/it] 89%|████████▉ | 17/19 [00:23<00:02, 1.27s/it] 95%|█████████▍| 18/19 [00:24<00:01, 1.21s/it] 100%|██████████| 19/19 [00:25<00:00, 1.04it/s] 100%|██████████| 19/19 [00:25<00:00, 1.33s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.3ms Speed: 3.2ms preprocess, 7.3ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:01<00:23, 1.32s/it] 11%|█ | 2/19 [00:02<00:25, 1.49s/it] 16%|█▌ | 3/19 [00:04<00:25, 1.60s/it] 21%|██ | 4/19 [00:06<00:22, 1.51s/it] 26%|██▋ | 5/19 [00:07<00:21, 1.51s/it] 32%|███▏ | 6/19 [00:09<00:19, 1.54s/it] 37%|███▋ | 7/19 [00:10<00:17, 1.50s/it] 42%|████▏ | 8/19 [00:12<00:16, 1.51s/it] 47%|████▋ | 9/19 [00:13<00:15, 1.54s/it] 53%|█████▎ | 10/19 [00:14<00:13, 1.46s/it] 58%|█████▊ | 11/19 [00:16<00:10, 1.37s/it] 63%|██████▎ | 12/19 [00:17<00:09, 1.36s/it] 68%|██████▊ | 13/19 [00:18<00:07, 1.31s/it] 74%|███████▎ | 14/19 [00:20<00:06, 1.31s/it] 79%|███████▉ | 15/19 [00:21<00:05, 1.27s/it] 84%|████████▍ | 16/19 [00:22<00:03, 1.27s/it] 89%|████████▉ | 17/19 [00:23<00:02, 1.27s/it] 95%|█████████▍| 18/19 [00:24<00:01, 1.21s/it] 100%|██████████| 19/19 [00:25<00:00, 1.04it/s] 100%|██████████| 19/19 [00:25<00:00, 1.32s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:01<00:24, 1.35s/it] 11%|█ | 2/19 [00:02<00:25, 1.50s/it] 16%|█▌ | 3/19 [00:04<00:25, 1.59s/it] 21%|██ | 4/19 [00:05<00:22, 1.49s/it] 26%|██▋ | 5/19 [00:07<00:21, 1.50s/it] 32%|███▏ | 6/19 [00:09<00:19, 1.54s/it] 37%|███▋ | 7/19 [00:10<00:17, 1.50s/it] 42%|████▏ | 8/19 [00:12<00:16, 1.52s/it] 47%|████▋ | 9/19 [00:13<00:15, 1.55s/it] 53%|█████▎ | 10/19 [00:15<00:13, 1.47s/it] 58%|█████▊ | 11/19 [00:16<00:11, 1.38s/it] 63%|██████▎ | 12/19 [00:17<00:09, 1.38s/it] 68%|██████▊ | 13/19 [00:18<00:07, 1.32s/it] 74%|███████▎ | 14/19 [00:20<00:06, 1.33s/it] 79%|███████▉ | 15/19 [00:21<00:05, 1.28s/it] 84%|████████▍ | 16/19 [00:22<00:03, 1.29s/it] 89%|████████▉ | 17/19 [00:23<00:02, 1.29s/it] 95%|█████████▍| 18/19 [00:24<00:01, 1.24s/it] 100%|██████████| 19/19 [00:25<00:00, 1.02it/s] 100%|██████████| 19/19 [00:25<00:00, 1.34s/it] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 3.0ms preprocess, 7.4ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:01<00:23, 1.33s/it] 11%|█ | 2/19 [00:02<00:25, 1.48s/it] 16%|█▌ | 3/19 [00:04<00:25, 1.59s/it] 21%|██ | 4/19 [00:05<00:22, 1.49s/it] 26%|██▋ | 5/19 [00:07<00:20, 1.50s/it] 32%|███▏ | 6/19 [00:09<00:19, 1.52s/it] 37%|███▋ | 7/19 [00:10<00:17, 1.48s/it] 42%|████▏ | 8/19 [00:11<00:16, 1.50s/it] 47%|████▋ | 9/19 [00:13<00:15, 1.54s/it] 53%|█████▎ | 10/19 [00:14<00:13, 1.46s/it] 58%|█████▊ | 11/19 [00:16<00:11, 1.38s/it] 63%|██████▎ | 12/19 [00:17<00:09, 1.38s/it] 68%|██████▊ | 13/19 [00:18<00:07, 1.33s/it] 74%|███████▎ | 14/19 [00:20<00:06, 1.33s/it] 79%|███████▉ | 15/19 [00:21<00:05, 1.28s/it] 84%|████████▍ | 16/19 [00:22<00:03, 1.28s/it] 89%|████████▉ | 17/19 [00:23<00:02, 1.28s/it] 95%|█████████▍| 18/19 [00:24<00:01, 1.22s/it] 100%|██████████| 19/19 [00:25<00:00, 1.03it/s] 100%|██████████| 19/19 [00:25<00:00, 1.33s/it] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.1ms Speed: 3.3ms preprocess, 7.1ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:01<00:24, 1.37s/it] 11%|█ | 2/19 [00:03<00:26, 1.54s/it] 16%|█▌ | 3/19 [00:04<00:25, 1.62s/it] 21%|██ | 4/19 [00:06<00:22, 1.51s/it] 26%|██▋ | 5/19 [00:07<00:21, 1.51s/it] 32%|███▏ | 6/19 [00:09<00:19, 1.54s/it] 37%|███▋ | 7/19 [00:10<00:17, 1.50s/it] 42%|████▏ | 8/19 [00:12<00:16, 1.51s/it] 47%|████▋ | 9/19 [00:13<00:15, 1.53s/it] 53%|█████▎ | 10/19 [00:14<00:13, 1.46s/it] 58%|█████▊ | 11/19 [00:16<00:10, 1.37s/it] 63%|██████▎ | 12/19 [00:17<00:09, 1.36s/it] 68%|██████▊ | 13/19 [00:18<00:07, 1.31s/it] 74%|███████▎ | 14/19 [00:20<00:06, 1.31s/it] 79%|███████▉ | 15/19 [00:21<00:05, 1.27s/it] 84%|████████▍ | 16/19 [00:22<00:03, 1.27s/it] 89%|████████▉ | 17/19 [00:23<00:02, 1.27s/it] 95%|█████████▍| 18/19 [00:24<00:01, 1.21s/it] 100%|██████████| 19/19 [00:25<00:00, 1.04it/s] 100%|██████████| 19/19 [00:25<00:00, 1.33s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 2 faces, 7.5ms Speed: 3.0ms preprocess, 7.5ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:01<00:23, 1.32s/it] 11%|█ | 2/19 [00:02<00:25, 1.48s/it] 16%|█▌ | 3/19 [00:04<00:25, 1.58s/it] 21%|██ | 4/19 [00:05<00:22, 1.48s/it] 26%|██▋ | 5/19 [00:07<00:20, 1.49s/it] 32%|███▏ | 6/19 [00:09<00:19, 1.52s/it] 37%|███▋ | 7/19 [00:10<00:17, 1.48s/it] 42%|████▏ | 8/19 [00:11<00:16, 1.50s/it] 47%|████▋ | 9/19 [00:13<00:15, 1.52s/it] 53%|█████▎ | 10/19 [00:14<00:13, 1.45s/it] 58%|█████▊ | 11/19 [00:15<00:10, 1.36s/it] 63%|██████▎ | 12/19 [00:17<00:09, 1.36s/it] 68%|██████▊ | 13/19 [00:18<00:07, 1.31s/it] 74%|███████▎ | 14/19 [00:19<00:06, 1.31s/it] 79%|███████▉ | 15/19 [00:20<00:05, 1.26s/it] 84%|████████▍ | 16/19 [00:22<00:03, 1.28s/it] 89%|████████▉ | 17/19 [00:23<00:02, 1.28s/it] 95%|█████████▍| 18/19 [00:24<00:01, 1.22s/it] 100%|██████████| 19/19 [00:25<00:00, 1.03it/s] 100%|██████████| 19/19 [00:25<00:00, 1.32s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:01<00:24, 1.36s/it] 11%|█ | 2/19 [00:03<00:26, 1.56s/it] 16%|█▌ | 3/19 [00:04<00:26, 1.65s/it] 21%|██ | 4/19 [00:06<00:22, 1.53s/it] 26%|██▋ | 5/19 [00:07<00:21, 1.52s/it] 32%|███▏ | 6/19 [00:09<00:20, 1.57s/it] 37%|███▋ | 7/19 [00:10<00:18, 1.52s/it] 42%|████▏ | 8/19 [00:12<00:16, 1.53s/it] 47%|████▋ | 9/19 [00:13<00:15, 1.56s/it] 53%|█████▎ | 10/19 [00:15<00:13, 1.48s/it] 58%|█████▊ | 11/19 [00:16<00:11, 1.39s/it] 63%|██████▎ | 12/19 [00:17<00:09, 1.38s/it] 68%|██████▊ | 13/19 [00:18<00:07, 1.33s/it] 74%|███████▎ | 14/19 [00:20<00:06, 1.34s/it] 79%|███████▉ | 15/19 [00:21<00:05, 1.29s/it] 84%|████████▍ | 16/19 [00:22<00:03, 1.29s/it] 89%|████████▉ | 17/19 [00:24<00:02, 1.28s/it] 95%|█████████▍| 18/19 [00:25<00:01, 1.22s/it] 100%|██████████| 19/19 [00:25<00:00, 1.03it/s] 100%|██████████| 19/19 [00:25<00:00, 1.34s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.1ms Speed: 3.1ms preprocess, 7.1ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. Uploading outputs... Finished.